MACHINE LEARNING FOR CLOSURE MODELS IN MULTIPHASE FLOW APPLICATIONS

@article{Buist2019MACHINELF,
  title={MACHINE LEARNING FOR CLOSURE MODELS IN MULTIPHASE FLOW APPLICATIONS},
  author={J. Buist and Benjamin Sanderse and Yous van Halder and Barry Koren and Gertjan van Heijst},
  journal={Proceedings of the 3rd International Conference on Uncertainty Quantification in Computational Sciences and Engineering (UNCECOMP 2019)},
  year={2019}
}
  • J. Buist, B. Sanderse, G. Heijst
  • Published 19 February 2019
  • Computer Science, Physics
  • Proceedings of the 3rd International Conference on Uncertainty Quantification in Computational Sciences and Engineering (UNCECOMP 2019)
Multiphase flows are described by the multiphase Navier-Stokes equations. Numerically solving these equations is computationally expensive, and performing many simulations for the purpose of design, optimization and uncertainty quantification is often prohibitively expensive. A simplified model, the so-called two-fluid model, can be derived from a spatial averaging process. The averaging process introduces a closure problem, which is represented by unknown friction terms in the two-fluid model… 
3 Citations
Machine Learning Augmented Two-Fluid Model for Segregated Flow
TLDR
The new model proposed in this work successfully captures the complex, dynamic, and non-linear relationships between the friction factor and flowing conditions and shows the best results from the proposed model.

References

SHOWING 1-10 OF 161 REFERENCES
Numerical simulation of roll waves in pipelines using the two-fluid model
textabstractA finite volume discretization of the incompressible two-fluid model in four-equation form is proposed for simulating roll waves appearing in multiphase pipelines. The new formulation has
A Machine Learning Strategy to Assist Turbulence Model Development
TLDR
This work investigates the feasibility of a new data-driven approach to turbulence model development by attempting to reproduce, through a machine learning methodology, the results obtained with the well-established Spalart-Allmaras model.
Constraint-consistent Runge-Kutta methods for one-dimensional incompressible multiphase flow
Closure relations of the one-dimensional two-fluid model for the simulation of slug flows
The present research is a development of an existing numerical methodology, based on a one-dimensional two-fluid model. This model is capable of simulating two-phase slug flow for horizontal and
A conservative fully implicit algorithm for predicting slug flows
...
...